webkit-ux-heuristics

webkit-ux-heuristics is a skill for Claude Code, Codex from aziontech/webkit. It costs 82 tokens per session (1,404 once invoked), scanned A, original, MIT.

A component-selection guide for designing user flows in an Azion web console. It maps common moments—such as loading, errors, empty results, confirmations, and overlays—to the matching interface component.

In plain words
What is it for?
Use it before building or reviewing a form, list, screen, or flow to choose components for loading states, field errors, empty results, confirmations, and focus-trapped overlays.
Why use it?
It prevents awkward flows caused by missing feedback, misplaced errors, unclear empty screens, or destructive actions without confirmation.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aziontech/webkit/webkit-ux-heuristics
Any agent
npx skills add aziontech/webkit --skill webkit-ux-heuristics
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for webkit-ux-heuristics

README.md
[![agentmods](https://agentmods.dev/badge/skills/aziontech/webkit/webkit-ux-heuristics.svg)](https://agentmods.dev/skills/aziontech/webkit/webkit-ux-heuristics)
Your own site
<a href="https://agentmods.dev/skills/aziontech/webkit/webkit-ux-heuristics"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-ux-heuristics.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00082 $0.01404
Opus 5 $0.00041 $0.00702
Sonnet 5 $0.00016 $0.00281
Haiku 4.5 $0.00008 $0.00140

Measured 4d ago against content hash e8a97f5fe6c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

webkit-ux-heuristics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/webkit/cli-templates/claude/skills/webkit-ux-heuristics/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: webkit-ux-heuristics

Purpose

Get the flow right before it is made to look good. Most UI slop is not a styling problem — it is a missing loading state, an error in the wrong place, an empty screen with no next step, or a destructive action with no confirmation. This is the discovery pass: for each moment in a flow, name the @aziontech/webkit component that already serves it, so you compose shipped behavior instead of hand-rolling it. Before polish, the flow must be sound.

Boundary: this skill picks the component per moment. How each state actually renders (the loading shape, the empty layout, the error affordance) and how async behavior sequences belong to /webkit-ui-states.

How to use

  • /webkit-ux-heuristics Apply the component map to any flow you design or build in this conversation.
  • /webkit-ux-heuristics <file> Review the file's flow against the map and output, per gap:
    • the exact line / element (quoted),
    • the moment it mishandles (1 short sentence),
    • the concrete fix, naming the webkit component to use.

When to invoke

  • Designing or reviewing a flow, form, list, or screen — before /webkit-baseline-ui / /webkit-motion-polish.
  • The user asks "is this good UX", "what am I missing", "review this flow".

Component map (the right tool per moment)

Each moment below is a Nielsen heuristic made concrete — the map is the checklist. Pick the component for the moment; don't re-derive the principle.

Moment Use Don't
Loading (content vs. inline) @aziontech/webkit/skeleton for content shape; the control's own loading / @aziontech/webkit/spinner for inline busy a bare full-page spinner for content that has a shape
Destructive / irreversible action @aziontech/webkit/dialog (confirm) a silent immediate action
Field validation error @aziontech/webkit/field-* + @aziontech/webkit/message next to the field a global toast for a field error
Page / section status @aziontech/webkit/message, @aziontech/webkit/status-indicator inventing a banner
Empty state @aziontech/webkit/button for the one next action + a one-line reason it's empty a dead-end "no results" string
Contextual actions / menu @aziontech/webkit/dropdown-menu a hand-rolled popover
Side surface @aziontech/webkit/panel, @aziontech/webkit/drawer a fixed div without focus management
Tooltip help @aziontech/webkit/tooltip title attribute only
Field label @aziontech/webkit/label placeholder-as-label

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 103 lines · 82 tokens per session scan A e8a97f5fe6c2

Subscribe to this mod's changes

webkit-ux-heuristics is a skill published in the GitHub repository aziontech/webkit (2 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,404 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

add-component

Add a SwiftUI component from ShipSwift. Use when the user says "add component", "add a view", "add X view", "I need a chart", "add animation", or wants a specific UI element.

signerlabs/ShipSwift · 48 tokens

design-motion-principles

Expert motion and interaction design auditor based on Emil Kowalski, Jakub Krehel, and Jhey Tompkins' techniques. Use when reviewing UI animations, transitions, hover states, or any motion design work. Provides per-designer perspectives with context-aware weighting.

uiNerd16/aicanvas · 60 tokens

design

Design workflow that creates design systems, DESIGN.md, and design tokens with anti-pattern enforcement and accessibility checks.

first-fluke/fullstack-starter · 22 tokens

better-design

Build, improve, and review production interfaces with the Better Design MCP. Use for frontend design, UI, UX, interactions, flows, forms, navigation, components, styling, design systems, accessibility, responsive layouts, motion, React Native, Expo, Shopify, Three.js, and product video work, especially when creating…

marvkr/better-design · 77 tokens

monorepo-management

Sets up or audits a monorepo workspace: tool selection, package naming, shared tooling, inter-package dependencies, selective CI, and versioning strategy. Invoked when the user asks to set up a monorepo, add a workspace, or manage multiple packages in a single repository.

soulcodex/agentic · 63 tokens

releasing

Authoring a changeset, or cutting a release for @vuetify/v0 and the @paper/ design systems. Use when writing a .changeset/.md file, deciding what belongs in changelog copy, re-entering or exiting changesets pre/beta mode, or reviewing a Version Packages PR. Covers the changeset content contract, the two version…

vuetifyjs/0 · 84 tokens